mlsanityData to 14 Oct 2026

CCD-3DR: Consistent Conditioning in Diffusion for Single-Image 3D Reconstruction

arXiv 2308.07837 ↗First posted 15 Aug 2023cs.CVcited by 10

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

In this paper, we present a novel shape reconstruction method leveraging diffusion model to generate 3D sparse point cloud for the object captured in a single RGB image. Recent methods typically leverage global embedding or local projection-based features as the condition to guide the diffusion model. However, such strategies fail to consistently align the denoised point cloud with the given image, leading to unstable conditioning and inferior performance. In this paper, we present CCD-3DR, which exploits a novel centered diffusion probabilistic model for consistent local feature conditioning. We constrain the noise and sampled point cloud from the diffusion model into a subspace where the point cloud center remains unchanged during the forward diffusion process and reverse process. The stable point cloud center further serves as an anchor to align each point with its corresponding local projection-based features. Extensive experiments on synthetic benchmark ShapeNet-R2N2 demonstrate that CCD-3DR outperforms all competitors by a large margin, with over 40% improvement. We also provide results on real-world dataset Pix3D to thoroughly demonstrate the potential of CCD-3DR in real-world applications. Codes will be released soon

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 52 of its 66 references that are in the map. First posted on arXiv 15 Aug 2023.

Builds on

52 of 66 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Point-E: A System for Generating 3D Point Clouds from Complex Prompts16 Dec
  2. 2022LION: Latent Point Diffusion Models for 3D Shape Generation12 Oct
  3. 2022DreamFusion: Text-to-3D using 2D Diffusion29 Sep
  4. 2021A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion7 Dec
  5. 2021Diffusion Probabilistic Models for 3D Point Cloud Generation2 Mar

Other references · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,403
  7. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  8. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
  9. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  10. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  11. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  12. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
35 more
  1. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  2. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,476
  3. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  4. 2020Improved Techniques for Training Score-Based Generative Modelscited by 1,043
  5. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 979
  6. 2018Pixel2Mesh: Generating 3D Mesh Models from Single RGB Imagescited by 651
  7. 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 588
  8. 2016Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modelingcited by 558
  9. 2018AtlasNet: A Papier-Mach'e Approach to Learning 3D Surface Generationcited by 539
  10. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  11. 2022GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Imagescited by 446
  12. 2019Point-Voxel CNN for Efficient 3D Deep Learningcited by 343
  13. 2019DISN: Deep Implicit Surface Network for High-quality Single-view 3D Reconstructioncited by 333
  14. 2023RealFusion: 360deg Reconstruction of Any Object from a Single Imagecited by 306
  15. 2021StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generationcited by 289
  16. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  17. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  18. 2017Learning a Multi-View Stereo Machinecited by 194
  19. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  20. 2019Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Imagescited by 164
  21. 2020Points2Surf: Learning Implicit Surfaces from Point Cloud Patchescited by 122
  22. 2017MarrNet: 3D Shape Reconstruction via 2.5D Sketchescited by 108
  23. 2019Deep Mesh Reconstruction from Single RGB Images via Topology Modification Networkscited by 106
  24. 2019Pixel2Mesh++: Multi-View 3D Mesh Generation via Deformationcited by 103
  25. 2018CubeSLAM: Monocular 3D Object SLAMcited by 102
  26. 2023PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstructioncited by 84
  27. 2020Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Imagescited by 79
  28. 2018Learning to Reconstruct Shapes from Unseen Classescited by 60
  29. 2014Category-Specific Object Reconstruction from a Single Imagecited by 56
  30. 2019Learning single-image 3D reconstruction by generative modelling of shape, pose and shadingcited by 43
  31. 2019Dense 3D Point Cloud Reconstruction Using a Deep Pyramid Networkcited by 33
  32. 2021LegoFormer: Transformers for Block-by-Block Multi-view 3D Reconstructioncited by 25
  33. 2022MonoGraspNet: 6-DoF Grasping with a Single RGB Imagecited by 24
  34. 2023ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistencycited by 16
  35. 2018Single-view Object Shape Reconstruction Using Deep Shape Prior and Silhouettecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 3; 2026: 1.

10 papers.

  1. 2025UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Modelscited by 39
  2. 2024Bayesian Diffusion Models for 3D Shape Reconstructioncited by 19
  3. 2024GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstructioncited by 18
  4. 2023DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Fieldcited by 17
  5. 2023MOHO: Learning Single-view Hand-held Object Reconstruction with Multi-view Occlusion-Aware Supervisioncited by 12
  6. 2024KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformationcited by 6
  7. 2025SeaLion: Semantic Part-Aware Latent Point Diffusion Models for 3D Generationcited by 4
  8. 2023D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstructioncited by 3
  9. 2025Consistency Diffusion Models for Single-Image 3D Reconstruction with Priorscited by 2
  10. 2026Point Diffusion Mamba: Unified Diffusion-State-Space Modeling for Single-View 3D Reconstruction under Data Scarcitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Coherent 3D Scene Diffusion From a Single RGB Image
  2. 2025Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
  3. 2024Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction
  4. 2025SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images
  5. 2026PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
  6. 20233D Colored Shape Reconstruction from a Single RGB Image through Diffusion
  7. 2023GECCO: Geometrically-Conditioned Point Diffusion Models
  8. 2026Meltdown: Circuits and Bifurcations in Point-Cloud-Conditioned 3D Diffusion Transformers